Research map / 3D vision / Human pose estimation
xR-EgoPose: Egocentric 3D Human Pose From an HMD Camera
Denis Tome, Patrick Peluse, Lourdes Agapito, Hernan Badino
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add second decoder branch that reconstructs input heatmaps (ablation) | Dual-branch auto-encoder lifting · xR-EgoPose test set (all actions) | MPJPE average (mm): 130.4 -> 58.2 | Improved |
| use proposed dual-branch lifting instead of Martinez et al. | xR-EgoPose lifting module · xR-EgoPose test set (all actions) | MPJPE average (mm): 122.1 -> 58.2 | Improved |
| add 100% 2D-only labels to 50% 3D labels (ablation) | Dual-branch auto-encoder · xR-EgoPose (50% 3D labels) | MPJPE (mm): 68.04 -> 63.98 | Improved |
| add COCO and MPII 2D annotations to H36M training (ablation) | Dual-branch auto-encoder · Human3.6M | MPJPE (mm): 67.9 -> 53.4 | Improved |
| use alternative 2D detectors (CPM, Stacked Hourglass) instead of ResNet101 (ablation) | 2D heatmap estimator · xR-EgoPose | MPJPE | No clear effect |
| use proposed method instead of Xu et al. on Mo2Cap2 indoor | Mo2Cap2 test set · Mo2Cap2 indoor | MPJPE total (mm): 61.40 -> 48.16 | Improved |
| use proposed method instead of Xu et al. on Mo2Cap2 outdoor | Mo2Cap2 test set · Mo2Cap2 outdoor | MPJPE total (mm): 80.64 -> 60.19 | Improved |
Closest papers by meaning
- SelfPose: 3D Egocentric Pose Estimation From a Headset Mounted Camera (TPAMI 2020 · similarity 0.98)
- Egocentric Pose Estimation From Human Vision Span (ICCV 2021 · similarity 0.92)
- 3D Human Pose Perception from Egocentric Stereo Videos (CVPR 2024 · similarity 0.90)
- EgoSim: An Egocentric Multi-view Simulator and Real Dataset for Body-worn Cameras during Motion and Activity (NeurIPS 2024 · similarity 0.89)
- FRAME: Floor-aligned Representation for Avatar Motion from Egocentric Video (CVPR 2025 · similarity 0.89)
- EgoGen: An Egocentric Synthetic Data Generator (CVPR 2024 · similarity 0.88)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
